A rule for generating and checking the agent-distribution files of an open-source project. These files help coding agents discover and use the project.

Use it to create or verify a Claude Code skill pack, scaffold plugin distribution files or run the skillpack command-line tool.

It helps ensure an open-source CLI or library has the packaging and checks needed to be discoverable by agents.

skillpack — Cursor rule by nordicnode

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add rules/nordicnode/skillpack/skillpack

Clone the repo

git clone --depth 1 https://github.com/nordicnode/skillpack

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.

When invoked 833 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00833
Opus 5	$0.00000	$0.00417
Sonnet 5	$0.00000	$0.00167
Haiku 4.5	$0.00000	$0.00083

Measured yesterday against content hash 50cea7c5a080, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skillpack scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/rules/skillpack.mdc · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

skillpack

Generate and verify the agent-distribution layer for any OSS project

When to use

Invoke this rule when the user's task matches any of these triggers:

generate a claude code skill pack
verify agent-discoverability of a CLI or library
scaffold claude plugin distribution files

When NOT to use

Do not use this rule if the user only wants to read or inspect skillpack without performing an action — prefer reading docs directly.
Do not use this rule for tasks outside the Rust tooling it was built for.

Installation

Ensure skillpack is installed and available on PATH before invoking the examples below.

Invocation

The exact command an agent should run to use this tool:

skillpack init

Run skillpack --help to discover the available flags. Documented flags (verified by skillpack verify):

--non-interactive
--verbose
--debug
--log-level
--log-format
-h
--help
-V
--version

Subcommands

This CLI uses subcommands. Each one has its own flags (verified by skillpack verify):

init — flags: --root, --non-interactive, --author, --invocation, --import, --accept-warnings, --auto, --license, --trigger, --description, --verbose, --debug, --log-level, --target, --force, --dry-run, --log-format, --template-dir, --format
verify — flags: --root, --format, --fix, --min-score, --watch, --template-dir, --verbose, --debug, --log-level, --log-format
doctor — flags: --root, --format, --verbose, --debug, --log-level, --log-format
update — flags: --root, --target, --force, --template-dir, --format, --verbose, --debug, --log-level, --log-format
diff — flags: --root, --target, --force, --template-dir, --format, --verbose, --debug, --log-level, --log-format
add — flags: --non-interactive, --root, --description, --trigger, --author, --invocation, --import, --license, --target, --force, --verbose, --debug, --log-level, --template-dir, --format, --log-format
remove — flags: --root, --target, --force, --template-dir, --format, --verbose, --debug, --log-level, --log-format
completions — flags: --verbose, --debug, --log-level, --log-format
config — flags: --root, --validate, --verbose, --debug, --log-level, --log-format

Read the full file on GitHub · 72 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday First seen · 72 lines · 0 tokens per session scan A 50cea7c5a080

Subscribe to this mod's changes

skillpack is a cursor rule published in the GitHub repository nordicnode/skillpack (2 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 833 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Languages agent-tools ai-agents claude claude-code cli developer-tools

skillpack

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

skillpack

When to use

When NOT to use

Installation

Invocation

Subcommands

What this file has done since we first saw it

Other cursor rules, from other repositories

angular-20

dev-standard

typescript

coolify-ai-docs

python_lib

specs